Accession Number:

ADA576841

Title:

Overcoming Vocabulary Limitations in Twitter Microblogs

Descriptive Note:

Conference paper

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA LANGUAGE TECHNOLOGIES INST

Personal Author(s):

• Kim, Yubin
• Yeniterzi, Reyyan
• Callan, Jamie

Report Date:

2012-11-01

Pagination or Media Count:

9.0

Abstract:

One major di culty in performing ad-hoc search on microblogs such as Twitter is the limited vocabulary of each document due their short length. In this paper, two approaches to addressing this issue are presented. The rst is query expansion through pseudo-relevance feedback and the other is document expansion of tweets using web documents linked from the body of the tweet. Tweets are expanded by concatenating the contents of the title tag and the meta descriptor tags of the document to the tweet itself. These two approaches gave additive gains in MAP and Precision at 30.

Descriptors:

• *INTERNET
• *VOCABULARY
• ADDRESSING
• LINKAGES
• SEARCHING

Subject Categories:

• Linguistics
• Computer Programming and Software

Distribution Statement:

APPROVED FOR PUBLIC RELEASE